# Mask-invariant Face Recognition through Template-level Knowledge Distillation arXiv: https://arxiv.org/abs/2112.05646 ยท HTML: https://mlsanity.com/paper/2112.05646/ ## Key facts - Cited by 10 papers in the map (data through 14 Oct 2026). - Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation. - Builds on 25 of its 49 references that are in the map. - First posted on arXiv 10 Dec 2021. ## Placed in - Knowledge distillation / [General knowledge distillation methods](https://mlsanity.com/distill/general-knowledge-distillation-methods/) ## Builds on (most cited first, 25 of 25) - [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015) - [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015) - [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015) - [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016) - [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017) - [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016) - [MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition](https://mlsanity.com/paper/1607.08221/) (2016) - [MagFace: A Universal Representation for Face Recognition and Quality Assessment](https://mlsanity.com/paper/2103.06627/) (2021) - [CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition](https://mlsanity.com/paper/2004.00288/) (2020) - [Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments](https://mlsanity.com/paper/1708.08197/) (2017) - [ElasticFace: Elastic Margin Loss for Deep Face Recognition](https://mlsanity.com/paper/2109.09416/) (2021) - [Low-resolution Face Recognition in the Wild via Selective Knowledge Distillation](https://mlsanity.com/paper/1811.09998/) (2018) - [Masked Face Recognition for Secure Authentication](https://mlsanity.com/paper/2008.11104/) (2020) - [Masked Face Recognition Challenge: The InsightFace Track Report](https://mlsanity.com/paper/2108.08191/) (2021) - [PocketNet: Extreme Lightweight Face Recognition Network using Neural Architecture Search and Multi-Step Knowledge Distillation](https://mlsanity.com/paper/2108.10710/) (2021) - [Self-restrained Triplet Loss for Accurate Masked Face Recognition](https://mlsanity.com/paper/2103.01716/) (2021) - [The Effect of Wearing a Mask on Face Recognition Performance: an Exploratory Study](https://mlsanity.com/paper/2007.13521/) (2020) - [MFR 2021: Masked Face Recognition Competition](https://mlsanity.com/paper/2106.15288/) (2021) - [Real Masks and Spoof Faces: On the Masked Face Presentation Attack Detection](https://mlsanity.com/paper/2103.01546/) (2021) - [Masked Face Recognition Challenge: The WebFace260M Track Report](https://mlsanity.com/paper/2108.07189/) (2021) - [Biometrics in the Era of COVID-19: Challenges and Opportunities](https://mlsanity.com/paper/2102.09258/) (2021) - [Masked Face Recognition: Human vs. Machine](https://mlsanity.com/paper/2103.01924/) (2021) - [My Eyes Are Up Here: Promoting Focus on Uncovered Regions in Masked Face Recognition](https://mlsanity.com/paper/2108.00996/) (2021) - [The Effect of Wearing a Face Mask on Face Image Quality](https://mlsanity.com/paper/2110.11283/) (2021) - [Occluded Face Recognition Using Low-rank Regression with Generalized Gradient Direction](https://mlsanity.com/paper/1906.02429/) (2019) ## Built on by (most cited first, 10 of 10) - [QuantFace: Towards Lightweight Face Recognition by Synthetic Data Low-bit Quantization](https://mlsanity.com/paper/2206.10526/) (2022) - [Causality-Inspired Taxonomy for Explainable Artificial Intelligence](https://mlsanity.com/paper/2208.09500/) (2022) - [OCFR 2022: Competition on Occluded Face Recognition From Synthetically Generated Structure-Aware Occlusions](https://mlsanity.com/paper/2208.02760/) (2022) - [Grouped Knowledge Distillation for Deep Face Recognition](https://mlsanity.com/paper/2304.04462/) (2023) - [Model Compression Techniques in Biometrics Applications: A Survey](https://mlsanity.com/paper/2401.10139/) (2024) - [A Survey on Computer Vision based Human Analysis in the COVID-19 Era](https://mlsanity.com/paper/2211.03705/) (2022) - [MST-KD: Multiple Specialized Teachers Knowledge Distillation for Fair Face Recognition](https://mlsanity.com/paper/2408.16563/) (2024) - [Masked Student Dataset of Expressions](https://mlsanity.com/paper/2304.03867/) (2023) - [Localization using Multi-Focal Spatial Attention for Masked Face Recognition](https://mlsanity.com/paper/2305.01905/) (2023) - [Seeing through the Mask: Multi-task Generative Mask Decoupling Face Recognition](https://mlsanity.com/paper/2311.11512/) (2023) ## Abstract (arXiv) The emergence of the global COVID-19 pandemic poses new challenges for biometrics. Not only are contactless biometric identification options becoming more important, but face recognition has also recently been confronted with the frequent wearing of masks. These masks affect the performance of previous face recognition systems, as they hide important identity information. In this paper, we propose a mask-invariant face recognition solution (MaskInv) that utilizes template-level knowledge distillation within a training paradigm that aims at producing embeddings of masked faces that are similar to those of non-masked faces of the same identities. In addition to the distilled knowledge, the student network benefits from additional guidance by margin-based identity classification loss, ElasticFace, using masked and non-masked faces. In a step-wise ablation study on two real masked face databases and five mainstream databases with synthetic masks, we prove the rationalization of our MaskInv approach. Our proposed solution outperforms previous state-of-the-art (SOTA) academic solutions in the recent MFRC-21 challenge in both scenarios, masked vs masked and masked vs non-masked, and also outperforms the previous solution on the MFR2 dataset. Furthermore, we demonstrate that the proposed model can still perform well on unmasked faces with only a minor loss in verification performance. The code, the trained models, as well as the evaluation protocol on the synthetically masked data are publicly available: https://github.com/fdbtrs/Masked-Face-Recognition-KD.